Glaucoma is an asymptomatic disease that can bring people to blindness if not early detected. Computational intelligence methods have been proposed to provide a computerized diagnosis that can guide patients to the appropriate treatment. However, these techniques face methodology optmization problems, which depends on the choices of many algorithms from diferent knowledge areas. This paper suggests a solution through meta-learning of preprocessing methods, decomposition and features extraction which have to be used efficiently in order to solve the problem. Current results are promissing, reaching 91.24% accuracy after 50 evaluations and it is suposed to improve proportionally to the number of evaluations.