This contribution approaches the problem of scratch restoration in old movies as an optimisation problem. The functional based on statistical properties of the image around the scratch is optimised using an ad-hoc genetic algorithm. Given the large amount of computational time needed by genetic algorithms, a network of standard workstations with heterogeneous operating systems has been used. Each workstation in the network works on each scratch to perform the restoration, and a specific machine works as a root node with the task of distributing jobs on the network and adding the outputted restored scratches back into the image.