This paper proposes a new methodology to compute Value at Risk (VaR) for quantifyinglosses in credit portfolios. We approximate the cumulative distribution of the loss function bya finite combination of Haar wavelet basis functions and calculate the coefficients of theapproximation by inverting its Laplace transform. The Wavelet Approximation (WA) methodis particularly suitable for non-smooth distributions, often arising in small or concentratedportfolios, when the hypothesis of the Basel II formulas are violated. To test the methodologywe consider the Vasicek one-factor portfolio credit loss model as our model framework. WA isan accurate, robust and fast method, allowing the estimation of the VaR much more quicklythan with a Monte Carlo (MC) method at the same level of accuracy and reliability.