The Negative Selection Algorithm is an immune inspired algorithm that can be used for different purposes such as fault detection, data integrity protection and virus detection. In this paper we show how the Negative Selection Algorithm can be adapted to tackle the similar image search problem: given a target image, images from a large database similar to the query have to be detected. Results of our experimental analysis indicate that the proposed algorithm is capable of detecting images similar to a target (self) image, given the right detectors. Source code and data used in the experiments are available on request.