We give efficient distributed algorithms for the minimum vertex cover problem in bipartite graphs in the CONGEST model. From Kőnig's theorem, it is well known that in bipartite graphs the size of a minimum vertex cover is equal to the size of a maximum matching. We first show that together with an existing $O(n\log n)$-round algorithm for computing a maximum matching, the constructive proof of Kőnig's theorem directly leads to a deterministic $O(n\log n)$-round CONGEST algorithm for computing a minimum vertex cover. We then show that by adapting the construction, we can also convert an \emph{approximate} maximum matching into an \emph{approximate} minimum vertex cover. Given a $(1-δ)$-approximate matching for some $δ>1$, we show that a $(1+O(δ))$-approximate vertex cover can be computed in time $O(D+\mathrm{poly}(\frac{\log n}δ))$, where $D$ is the diameter of the graph. When combining with known graph clustering techniques, for any $\varepsilon\in(0,1]$, this leads to a $\mathrm{poly}(\frac{\log n}{\varepsilon})$-time deterministic and also to a slightly faster and simpler randomized $O(\frac{\log n}{\varepsilon^3})$-round CONGEST algorithm for computing a $(1+\varepsilon)$-approximate vertex cover in bipartite graphs. For constant $\varepsilon$, the randomized time complexity matches the $Ω(\log n)$ lower bound for computing a $(1+\varepsilon)$-approximate vertex cover in bipartite graphs even in the LOCAL model. Our results are also in contrast to the situation in general graphs, where it is known that computing an optimal vertex cover requires $\tildeΩ(n^2)$ rounds in the CONGEST model and where it is not even known how to compute any $(2-\varepsilon)$-approximation in time $o(n^2)$.