The topics addressed in this paper are threefold: First, techniques for the semiautomatic normalization of image descriptors in a digital image collection from free text titles and keywords. Second, the efficient construction of thesauri for specific image collections. And third, the optimisation of search mechanisms to deal with the special characteristics of the image collections and with the use made by users through web-based search interfaces. The solutions presented here have been developed in the framework of a commercial project intended to improve image search in a website for selling photographs through the web. The ultimate goal of this project is to improve the customer accessibility to a collection of more than two million photographs.