In real world applications one often has to deal with problems, involving a few hundreds of features. These problems are a great challenge, as the overall complexity is rapidly increasing with the number of features. Feature selection is concerned with the identification of those features, that are necessary to solve a given problem using as few features as possible.In this paper we will present a novel approach to feature selection using bacterial optimization. First, we will describe the bacterial optimization used, then we will show, how this method can be used for the task of feature selection. Finally, some simulation results are presented, to show the potential of this new approach.