The amount of audio-visual information has increased dramatically with the advent of High Speed Internet. Furthermore, technological advances in recent years in the field of information technology, have simplified the use of video data in various fields by the general public. This made it possible to store large collections of video documents into computer systems. To enable efficient use of these collections, it is necessary to develop tools to facilitate access to these documents and handling them. In this paper we propose a method for indexing and retrieval of video sequences in a video database of large dimension, based on a weighting technique to calculate the degree of membership of a concept in a video also a structuring of the data of the audio-visual (context / concept / video) and a relevance feedback mechanism.