This paper implements the answer-copying detection methodology for multiple-choice tests developed in Sotaridona, van der Linden and Meijer [2006], based on Cohen's Kappa index. We present results of this methodology applied to the standardized test for college admissions in Colombia that took place in the second semester of 2009. This is, to the authors' knowledge, the first study in Colombia that seeks to provide quantitative tools, of statistical nature, to detect fraud. This paper also evaluates, with real data, the performance of the Kappa index proposed in the referenced paper, which had only been evaluated using simulated data generated with a nominal item response model. In particular, we find evidence that there are misspecification problems that are difficult to overcome when using real data. We hope this paper motivates further applied research in this field in Colombia.