Ontology matching consists of finding the semantic relations between different ontologies and is wedely recognized as an essential process to achieve and adequate interoperability between people, systems or organizations that use different, overlapping ontologies to represent the same knowledge. There are several techniques to mesaure the semantic similarity of elemsts from separate ontologies, which must be adequately combied in order to obtain precise and complete results. Nevertheless, combining multiple similarity mesures into a single metric is a complex problema, which has been traidionally solved using weights determined manually by and expert, or thorough general methods that do not provide optimal results. In this paper, a genetic algorithms-based approach to aggregate different similarity metrics into a single function is presented. Starting form an initial population of individuls, each one representing a combinatiuon of similarity measures, our approach allows to find the combination that provides the optimal matching quality.