Modern big data systems run on cloud environments where resources are shared amongst several users and applications. As a result, declarative user queries in these environments need to be optimized and executed over resources that constantly change and are provisioned on demand for each job. This requires us to rethink traditional query optimizers designed for systems that run on dedicated resources. In this paper, we show evidence that the choice of query plans depends heavily on the available resources, and the current practice of choosing query plans before picking the resources could lead to significant performance loss in two popular big data systems, namely Hive and SparkSQL. Therefore, we make a case for Resource and Query Optimization (or RAQO), i.e., choosing both the query plan and the resource configuration at the same time. We describe rule-based RAQO and present alternate decisions trees to make resource-aware query planning in Hive and Spark. We further present cost-based RAQO that integrates resource planning within a query planner, and show techniques to significantly reduce the resource planning overheads. We evaluate cost-based RAQO using state-of-the-art System R query planner as well as a recently proposed multi-objective query planner. Our evaluation on TPC-H and randomly generated schemas show that: (i) we can reduce the resource planning overhead by up to 16x, and (ii) RAQO can scale to schemas as large as 100 table joins as well as clusters as big as 100K containers with 100GB each.